Select and Trade: Towards Unified Pair Trading with Hierarchical Reinforcement Learning

  title={Select and Trade: Towards Unified Pair Trading with Hierarchical Reinforcement Learning},
  author={Weiguang Han and Boyi Zhang and Qianqian Xie and Min Peng and Yanzhao Lai and Jimin Huang},
Pair trading is one of the most effective statistical arbitrage strategies which seeks a neutral profit by hedging a pair of selected assets. Existing methods generally decompose the task into two separate steps: pair selection and trading. However, the decoupling of two closely related subtasks can block information propagation and lead to limited overall performance. For pair selection, ignoring the trading performance results in the wrong assets being selected with irrelevant price movements… 

Figures and Tables from this paper

Mastering Pair Trading with Risk-Aware Recurrent Reinforcement Learning

Although pair trading is the simplest hedging strategy for an investor to eliminate market risk, it is still a great challenge for reinforcement learning (RL) methods to perform pair trading as human

Improving Pairs Trading Strategies via Reinforcement Learning

This study investigates the possibility of using deep reinforcement learning to enhance pairs trading performance and proposes a simple yet effective reward shaping method that takes a baseline policy as input, which demonstrates that RL models can achieve higher return and Sharpe ratio than traditional strategies.

Optimizing the Pairs-Trading Strategy Using Deep Reinforcement Learning with Trading and Stop-Loss Boundaries

This study proposes an optimized pairs-trading strategy using deep reinforcement learning—particularly with the deep Q-network—utilizing various trading and stop-loss boundaries and finds that the proposed model is trained well and outperforms traditional pairs-Trading strategies.

Hybrid Deep Reinforcement Learning for Pairs Trading

A hybrid deep reinforcement learning method for pairs trading called HDRL-Trader is proposed, which employs two independent reinforcement learning networks; one for determining trading actions and the other for determining stop-loss boundaries.

Deep Reinforcement Learning Pairs Trading with a Double Deep Q-Network

  • Andrew Brim
  • Computer Science
    2020 10th Annual Computing and Communication Workshop and Conference (CCWC)
  • 2020
Attesting that a reinforcement learning system, can effectively learn and execute a pairs trading strategy in the stock market, and introduces a parameter, Negative Rewards Multiplier, during training that adjusts the system's ability to take more conservative actions.

Structural break-aware pairs trading strategy using deep reinforcement learning

A two-phase pair trading strategy optimization framework, namely structural break-aware pairs trading strategy (SAPT), which outperforms the state-of-the-art strategies by at least 456% and 934% in terms of profit and Sortino ratio, respectively.

Pairs trading strategy optimization using the reinforcement learning method: a cointegration approach

This paper examines the optimum level of pairs trading specifications over time using reinforcement learning to find that boosting pairs trading Specifications by using the proposed approach significantly overperform the previous methods.

Reinforcement learning in financial markets - a survey

The present paper draws insights from almost 50 publications, and categorizes them into three main approaches, i.e., critic-only approach, actor- only approach, and actor-critic approach, which help identify recurring design decisions as well as potential levers to improve the agent's performance.

Dynamic Portfolio Management Based on Pair Trading and Deep Reinforcement Learning

An experiment on the Chinese A-share market showed that the proposed pair-based deep portfolio model has superiority for dynamic portfolio management problem in trade-off investment returns and risks.

M of a Kind: A Multivariate Approach at Pairs Trading

The main conclusion of the paper is that the proposed version of pairs trading, which will try to create an artificial pair for a particular stock based on the information of m assets, was able to beat the benchmark returns and random portfolios for the majority of the parameters.

Finding the Optimal Pre-set Boundaries for Pairs Trading Strategy Based on Cointegration Technique

Pairs trading is one of the arbitrage strategies that can be used in trading stocks on the stock market. This paper incorporates pairs trading with the use of cointegration technique to exploit